Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization
- URL: http://arxiv.org/abs/2501.04102v1
- Date: Tue, 07 Jan 2025 19:19:22 GMT
- Title: Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalization
- Authors: Song Wang, Xiaodong Yang, Rashidul Islam, Huiyuan Chen, Minghua Xu, Jundong Li, Yiwei Cai,
- Abstract summary: We introduce an innovative approach that aims to enhance two types of consistency for graph OOD generalization.
With the augmented graphs, we enrich the training data without compromising the integrity of label-graph relationships.
We conduct extensive experiments on real-world datasets to demonstrate the superiority of our framework over other state-of-the-art baselines.
- Score: 45.84955654481374
- License:
- Abstract: To deal with distribution shifts in graph data, various graph out-of-distribution (OOD) generalization techniques have been recently proposed. These methods often employ a two-step strategy that first creates augmented environments and subsequently identifies invariant subgraphs to improve generalizability. Nevertheless, this approach could be suboptimal from the perspective of consistency. First, the process of augmenting environments by altering the graphs while preserving labels may lead to graphs that are not realistic or meaningfully related to the origin distribution, thus lacking distribution consistency. Second, the extracted subgraphs are obtained from directly modifying graphs, and may not necessarily maintain a consistent predictive relationship with their labels, thereby impacting label consistency. In response to these challenges, we introduce an innovative approach that aims to enhance these two types of consistency for graph OOD generalization. We propose a modifier to obtain both augmented and invariant graphs in a unified manner. With the augmented graphs, we enrich the training data without compromising the integrity of label-graph relationships. The label consistency enhancement in our framework further preserves the supervision information in the invariant graph. We conduct extensive experiments on real-world datasets to demonstrate the superiority of our framework over other state-of-the-art baselines.
Related papers
- Generative Risk Minimization for Out-of-Distribution Generalization on Graphs [71.48583448654522]
We propose an innovative framework, named Generative Risk Minimization (GRM), designed to generate an invariant subgraph for each input graph to be classified, instead of extraction.
We conduct extensive experiments across a variety of real-world graph datasets for both node-level and graph-level OOD generalization.
arXiv Detail & Related papers (2025-02-11T21:24:13Z) - Subgraph Aggregation for Out-of-Distribution Generalization on Graphs [29.884717215947745]
Out-of-distribution (OOD) generalization in Graph Neural Networks (GNNs) has gained significant attention.
We propose a novel framework, SubGraph Aggregation (SuGAr), designed to learn a diverse set of subgraphs.
Experiments on both synthetic and real-world datasets demonstrate that SuGAr outperforms state-of-the-art methods.
arXiv Detail & Related papers (2024-10-29T16:54:37Z) - Collaborate to Adapt: Source-Free Graph Domain Adaptation via
Bi-directional Adaptation [40.25858820407687]
Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph.
We present a novel paradigm called GraphCTA, which performs model adaptation and graph adaptation collaboratively.
Our proposed model outperforms recent source-free baselines by large margins.
arXiv Detail & Related papers (2024-03-03T10:23:08Z) - Mind the Label Shift of Augmentation-based Graph OOD Generalization [88.32356432272356]
LiSA exploits textbfLabel-textbfinvariant textbfSubgraphs of the training graphs to construct textbfAugmented environments.
LiSA generates diverse augmented environments with a consistent predictive relationship.
Experiments on node-level and graph-level OOD benchmarks show that LiSA achieves impressive generalization performance with different GNN backbones.
arXiv Detail & Related papers (2023-03-27T00:08:45Z) - Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
Contrastive learning has emerged as a premier method for learning representations with or without supervision.
Recent studies have shown its utility in graph representation learning for pre-training.
We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
arXiv Detail & Related papers (2023-02-06T16:26:29Z) - Invariance Principle Meets Out-of-Distribution Generalization on Graphs [66.04137805277632]
Complex nature of graphs thwarts the adoption of the invariance principle for OOD generalization.
domain or environment partitions, which are often required by OOD methods, can be expensive to obtain for graphs.
We propose a novel framework to explicitly model this process using a contrastive strategy.
arXiv Detail & Related papers (2022-02-11T04:38:39Z) - A Robust and Generalized Framework for Adversarial Graph Embedding [73.37228022428663]
We propose a robust framework for adversarial graph embedding, named AGE.
AGE generates the fake neighbor nodes as the enhanced negative samples from the implicit distribution.
Based on this framework, we propose three models to handle three types of graph data.
arXiv Detail & Related papers (2021-05-22T07:05:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.